Instructions to use 64bits/LexPodLM-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 64bits/LexPodLM-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="64bits/LexPodLM-13B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("64bits/LexPodLM-13B") model = AutoModelForCausalLM.from_pretrained("64bits/LexPodLM-13B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use 64bits/LexPodLM-13B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "64bits/LexPodLM-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "64bits/LexPodLM-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/64bits/LexPodLM-13B
- SGLang
How to use 64bits/LexPodLM-13B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "64bits/LexPodLM-13B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "64bits/LexPodLM-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "64bits/LexPodLM-13B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "64bits/LexPodLM-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use 64bits/LexPodLM-13B with Docker Model Runner:
docker model run hf.co/64bits/LexPodLM-13B
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,8 @@ LexPodLM-13B is a LLaMA-13B model fine-tuned using Vicuna's schema, with this da
|
|
| 14 |
|
| 15 |
While it might not excel in tasks like code writing, fact searching, or essay writing, it can potentially serve as an effective chat model, capable of providing verbose and nuanced responses.
|
| 16 |
|
|
|
|
|
|
|
| 17 |
|
| 18 |
***
|
| 19 |
*Human: do you think consciousness is foundamentally computational?*
|
|
|
|
| 14 |
|
| 15 |
While it might not excel in tasks like code writing, fact searching, or essay writing, it can potentially serve as an effective chat model, capable of providing verbose and nuanced responses.
|
| 16 |
|
| 17 |
+
***
|
| 18 |
+
I trained the model on 4 A100 (80 GB RAM) for ~15 hrs.
|
| 19 |
|
| 20 |
***
|
| 21 |
*Human: do you think consciousness is foundamentally computational?*
|